Multicore systems on-chip : practical software/hardware design / / Abderazek Ben Abdallah |
Autore | Ben Abdallah Abderazek |
Edizione | [1st ed. 2013.] |
Pubbl/distr/stampa | Paris : , : Atlantis Press, , 2013 |
Descrizione fisica | 1 online resource (xxvi, 273 pages) : illustrations (some color) |
Disciplina |
004.21
006.2 006.2/2 |
Collana | Atlantis Ambient and Pervasive Intelligence |
Soggetto topico |
Systems on a chip - Design and construction
Networks on a chip Ubiquitous computing Embedded computer systems |
ISBN | 94-91216-92-9 |
Formato | Materiale a stampa |
Livello bibliografico | Monografia |
Lingua di pubblicazione | eng |
Nota di contenuto | Introduction to Multicore Systems On-Chip -- Multicore SoCs Design Methods -- Multicore SoC Organization -- 2D Network-on-Chip -- 3D Network-on-Chip -- Network Interface Architecture and Design for 2D/3D NoCs -- Parallelizing Compiler for Single and Multicore Computing -- Power Optimization Techniques for Multicore SoCs -- Soft-Core Processor for Low-Power Embedded -- Dual-Execution Processor Architecture for Embedded -- Case Study: Deign of Embedded Multicore SoC. |
Record Nr. | UNINA-9910437959803321 |
Ben Abdallah Abderazek | ||
Paris : , : Atlantis Press, , 2013 | ||
Materiale a stampa | ||
Lo trovi qui: Univ. Federico II | ||
|
System-level modelling and design space exploration for multiprocessor embedded system-on-chip architectures [[electronic resource] /] / Cagkan Erbas |
Autore | Erbaş Çağkan |
Pubbl/distr/stampa | Amsterdam, : Amsterdam University Press, c2006 |
Descrizione fisica | 1 online resource (154 p.) |
Disciplina | 621.3815 |
Soggetto topico |
Systems on a chip - Design and construction
Computer architecture |
Soggetto genere / forma | Electronic books. |
ISBN |
1-280-95862-6
9786610958627 90-485-0471-6 1-4294-5460-1 |
Formato | Materiale a stampa |
Livello bibliografico | Monografia |
Lingua di pubblicazione | eng |
Nota di contenuto | Acknowledgments; 1 Introduction; 2 The Sesame environment; 3 Multiobjective application mapping; 4 Dataflow-based trace transformations; 5 Motion-JPEG encoder case studies; 6 Real-time issues; 7 Conclusion; A Performance metrics; B Task systems; References; Nederlandse samenvatting; Scientific output; Biography; Table of Contents |
Record Nr. | UNINA-9910451876103321 |
Erbaş Çağkan | ||
Amsterdam, : Amsterdam University Press, c2006 | ||
Materiale a stampa | ||
Lo trovi qui: Univ. Federico II | ||
|
System-level modelling and design space exploration for multiprocessor embedded system-on-chip architectures [[electronic resource] /] / Cagkan Erbas |
Autore | Erbaş Çağkan |
Pubbl/distr/stampa | Amsterdam, : Amsterdam University Press, c2006 |
Descrizione fisica | 1 online resource (154 p.) |
Disciplina | 621.3815 |
Soggetto topico |
Systems on a chip - Design and construction
Computer architecture |
ISBN |
1-280-95862-6
9786610958627 90-485-0471-6 1-4294-5460-1 |
Formato | Materiale a stampa |
Livello bibliografico | Monografia |
Lingua di pubblicazione | eng |
Nota di contenuto | Acknowledgments; 1 Introduction; 2 The Sesame environment; 3 Multiobjective application mapping; 4 Dataflow-based trace transformations; 5 Motion-JPEG encoder case studies; 6 Real-time issues; 7 Conclusion; A Performance metrics; B Task systems; References; Nederlandse samenvatting; Scientific output; Biography; Table of Contents |
Record Nr. | UNINA-9910777895703321 |
Erbaş Çağkan | ||
Amsterdam, : Amsterdam University Press, c2006 | ||
Materiale a stampa | ||
Lo trovi qui: Univ. Federico II | ||
|
System-level modelling and design space exploration for multiprocessor embedded system-on-chip architectures [[electronic resource] /] / Cagkan Erbas |
Autore | Erbaş Çağkan |
Edizione | [1st ed.] |
Pubbl/distr/stampa | Amsterdam, : Amsterdam University Press, c2006 |
Descrizione fisica | 1 online resource (154 p.) |
Disciplina | 621.3815 |
Soggetto topico |
Systems on a chip - Design and construction
Computer architecture |
ISBN |
1-280-95862-6
9786610958627 90-485-0471-6 1-4294-5460-1 |
Formato | Materiale a stampa |
Livello bibliografico | Monografia |
Lingua di pubblicazione | eng |
Nota di contenuto | Acknowledgments; 1 Introduction; 2 The Sesame environment; 3 Multiobjective application mapping; 4 Dataflow-based trace transformations; 5 Motion-JPEG encoder case studies; 6 Real-time issues; 7 Conclusion; A Performance metrics; B Task systems; References; Nederlandse samenvatting; Scientific output; Biography; Table of Contents |
Record Nr. | UNINA-9910808596903321 |
Erbaş Çağkan | ||
Amsterdam, : Amsterdam University Press, c2006 | ||
Materiale a stampa | ||
Lo trovi qui: Univ. Federico II | ||
|
Towards Heterogeneous Multi-Core Systems-on-Chip for Edge Machine Learning : Journey from Single-Core Acceleration to Multi-core Heterogeneous Systems / / Vikram Jain and Marian Verhelst |
Autore | Jain Vikram |
Edizione | [First edition.] |
Pubbl/distr/stampa | Cham, Switzerland : , : Springer, , [2024] |
Descrizione fisica | 1 online resource (199 pages) |
Disciplina | 005.758 |
Soggetto topico |
Edge computing
Machine learning Systems on a chip - Design and construction |
ISBN | 3-031-38230-7 |
Formato | Materiale a stampa |
Livello bibliografico | Monografia |
Lingua di pubblicazione | eng |
Nota di contenuto |
Intro -- Preface -- Acknowledgments -- Contents -- List of Abbreviations -- List of Figures -- List of Tables -- 1 Introduction -- 1.1 Machine Learning at the (Extreme) Edge -- 1.1.1 Applications -- 1.1.2 Algorithms -- 1.1.3 Hardware -- 1.2 Open Challenges for ML Acceleration at the (Extreme) Edge -- 1.3 Book Contributions -- 2 Algorithmic Background for Machine Learning -- 2.1 Support Vector Machines -- 2.2 Deep Learning Models -- 2.2.1 Neural Networks -- 2.2.2 Training -- 2.2.3 Inference: Neural Network Topologies -- 2.2.4 Model Compression -- 2.3 Feature Extraction -- 2.4 Conclusion -- 3 Scoping the Landscape of (Extreme) Edge Machine Learning Processors -- 3.1 Hardware Acceleration of ML Workloads: A Primer -- 3.1.1 Core Mathematical Operation -- 3.1.2 General Accelerator Template -- 3.2 Evaluation Metrics -- 3.3 Survey of (Extreme) Edge ML Hardware Platforms -- 3.4 Evaluating the Surveyed Hardware Platforms -- 3.5 Insights and Trends -- 3.6 Conclusion -- 4 Hardware-Software Co-optimization Through Design Space Exploration -- 4.1 Motivation -- 4.2 Exploration Methodology -- 4.2.1 ZigZag -- 4.2.2 Post-Processing of ZigZag's Results -- 4.3 DNN Workload Comparison -- 4.3.1 Exploration Setup -- 4.3.2 Visualization of the Complete Trade-Off Space -- 4.3.3 Impact of HW Architecture on Optimal Workload -- 4.3.4 Impact of Workload on Optimal HW Architecture -- 4.4 Conclusion -- 5 Energy-Efficient Single-Core Hardware Acceleration -- 5.1 Motivation -- 5.2 Metrics for Hardware Optimization -- 5.3 State-of-the-Art in Object Detection on FPGA -- 5.4 Cost-Aware Algorithmic Optimization -- 5.4.1 Object Detection Algorithms -- 5.4.2 Quantization of Tiny-YOLOv2 -- Post-training Quantization -- Quantization-Aware Training -- 5.5 Cost-Aware Architecture Optimization -- 5.5.1 Hardware Mapping of Convolutional Layers.
5.5.2 Hardware Architecture of the Accelerator -- 5.6 Cost-Aware System Optimization -- 5.6.1 Data Communication Architecture -- 5.6.2 Tiling Strategy -- 5.7 Implementation Results -- 5.8 Conclusion -- 6 TinyVers: A Tiny Versatile All-Digital Heterogeneous Multi-core System-on-Chip -- 6.1 Motivation -- 6.2 Algorithmic Background -- 6.2.1 Convolution and Dense Operation -- 6.2.2 Deconvolution -- 6.2.3 Support Vector Machines (SVMs) -- 6.3 TinyVers Hardware Architecture -- 6.3.1 Smart Sensing Modes for TinyML -- 6.3.2 Power Management -- 6.4 FlexML Accelerator -- 6.4.1 FlexML Architecture Overview -- 6.4.2 Dataflow Reconfiguration -- 6.4.3 Efficient Zero-Skipping for Deconvolution and Blockwise Structured Sparsity -- 6.4.4 Support Vector Machine -- 6.5 Deployment of Neural Networks on TinyVers -- 6.6 Design for Test and Fault-Tolerance -- 6.7 Chip Implementation and Measurement -- 6.7.1 Peak Performance Analysis -- 6.7.2 Workload Benchmarks -- 6.7.3 Power Management -- 6.7.4 Instantaneous Power Trace -- Keyword Spotting Application -- Machine Monitoring Application -- 6.8 Comparison with SotA -- 6.9 Conclusion -- 7 DIANA: DIgital and ANAlog Heterogeneous Multi-core System-on-Chip -- 7.1 Motivation -- 7.2 Design Choices -- 7.2.1 Dataflow Concepts -- 7.2.2 Design Space Exploration -- 7.2.3 A Reconfigurable Heterogeneous Architecture -- 7.2.4 Optimization Strategies for Multi-core -- 7.3 System Architecture -- 7.3.1 The RISC-V CPU and Network Control -- 7.3.2 Memory System -- 7.4 AIMC Computing Core -- 7.4.1 AIMC Core Microarchitecture -- 7.4.2 Memory Control Unit (MCU) -- 7.4.3 AIMC Macro -- 7.4.4 Output Buffer and SIMD Unit -- 7.5 Digital DNN Accelerator -- 7.6 Measurements -- 7.6.1 Efficiency vs. Accuracy Trade-Off in the Analog Macro -- 7.6.2 Peak Performance and Efficiency Characterization -- 7.6.3 Workload Performance Characterization. 7.6.4 SotA Comparison -- 7.7 Conclusion -- 8 Networks-on-Chip to Enable Large-Scale Multi-core ML Acceleration -- 8.1 Motivation -- 8.2 Background -- 8.2.1 Network-on-Chips -- 8.2.2 AXI Protocol -- Burst -- Multiple Outstanding Transaction -- 8.3 Interconnect Architecture of PATRONoC -- 8.4 Implementation Results -- 8.5 Performance Evaluation -- 8.5.1 Uniform Random Traffic -- 8.5.2 Synthetic Traffic -- 8.5.3 DNN Workload Traffic -- 8.6 Related Work -- 8.7 Conclusion -- 9 Conclusion -- 9.1 Overview and Contributions -- 9.2 Suggestions for Future Work -- 9.2.1 The Low Hanging Fruits -- 9.2.2 Medium Term -- 9.2.3 Moonshot -- 9.3 Closing Remarks -- References -- References -- Index. |
Record Nr. | UNINA-9910760277003321 |
Jain Vikram | ||
Cham, Switzerland : , : Springer, , [2024] | ||
Materiale a stampa | ||
Lo trovi qui: Univ. Federico II | ||
|